The "main_supervised_baseline.py" is the python script to run experiments with arguments with the following example.

--python main_supervised_baseline.py --dataset 'chapman' --backbone 'resnet' --block 8 --batch_size 32  --lr 5e-4 --n_epoch 999 --cuda 2 --stride 2 --controller

To check the consistency for shift-invariancy,

--python main_supervised_baseline.py --dataset 'chapman' --backbone 'resnet' --block 8 --batch_size 32  --lr 5e-4 --n_epoch 999 --cuda 2 --stride 2 --controller --robust_check

To check the low-pass filtering,

--python main_supervised_baseline.py --dataset 'chapman' --backbone 'resnet' --block 8 --batch_size 32  --lr 5e-4 --n_epoch 999 --cuda 2 --stride 2 --blur

And, for polyphase subsampling

--python main_supervised_baseline.py --dataset 'chapman' --backbone 'resnet' --block 8 --batch_size 32  --lr 5e-4 --n_epoch 999 --cuda 2 --stride 2 --aps


Scripts for low-pass filtering (anti-aliasing) and polyphase can be found under the models folder as "blurpool.py" and "apspool.py", respectively.


while the structure of learning comes from "https://github.com/Tian0426/CL-HAR" and "https://github.com/eth-siplab/Finding_Order_in_Chaos". 

@inproceedings{10.1145/3534678.3539134,
author = {Qian, Hangwei and Tian, Tian and Miao, Chunyan},
title = {What Makes Good Contrastive Learning on Small-Scale Wearable-Based Tasks?},
year = {2022},
isbn = {9781450393850},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3534678.3539134},
doi = {10.1145/3534678.3539134},
booktitle = {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {3761–3771},
numpages = {11},
series = {KDD '22}
}

@inproceedings{
demirel2023finding,
title={Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning},
author={Berken Utku Demirel and Christian Holz},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=dbVRDk2wt7}
}

Both are cited in the paper.

